Parallel Ant Colony Optimization Algorithm on a Multi-core Processor

Parallel Ant Colony Optimization Algorithm on a Multi-core Processor
复制标题

DOI:
10.1007/978-3-642-15461-4_48
复制
发表时间:
2010-09
期刊:
--
影响因子:
--
通讯作者:
S. Tsutsui;N. Fujimoto
S. Tsutsui;N. Fujimoto
中科院分区:
其他
文献类型:
--
作者:
S. Tsutsui;N. Fujimoto

文献摘要

被引文献

相似文献

提出了蚁群优化算法在多核处理器计算平台上的并行化方法,旨在快速执行,以找到可接受的解决方案。作为蚁群优化算法,我们使用了巧妙的蚂蚁系统,并在几种规模的TSP实例上进行了测试。作为并行化方法,我们使用代理级并行在一个群体中使用Java线程编程。根据线程间的同步和排他控制方式,提出了三种并行蚁群算法。其中,我们称之为粗糙异步并行模型显示了最有前途的结果。
This paper proposes parallelization methods of ACO algorithms on a computing platform with a multi-core processor aiming at fast execution to find acceptable solutions. As an ACO algorithm, we use the cunning Ant System and test on several sizes of TSP instances. As the parallelization method, we use agent level parallelization in one colony using Java thread programming. According to the synchronization and exclusive control modes among threads, we propose three types of parallel ACO algorithms. Among them, that which we call the rough asynchronous parallel model shows the most promising results.